Text Generation
Transformers
Safetensors
English
Chinese
qwen3
rm
cr
conversational
text-generation-inference
Instructions to use codefuse-ai/SWE-CARE-RM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codefuse-ai/SWE-CARE-RM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="codefuse-ai/SWE-CARE-RM") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/SWE-CARE-RM") model = AutoModelForCausalLM.from_pretrained("codefuse-ai/SWE-CARE-RM") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use codefuse-ai/SWE-CARE-RM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "codefuse-ai/SWE-CARE-RM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codefuse-ai/SWE-CARE-RM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/codefuse-ai/SWE-CARE-RM
- SGLang
How to use codefuse-ai/SWE-CARE-RM with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "codefuse-ai/SWE-CARE-RM" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codefuse-ai/SWE-CARE-RM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "codefuse-ai/SWE-CARE-RM" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codefuse-ai/SWE-CARE-RM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use codefuse-ai/SWE-CARE-RM with Docker Model Runner:
docker model run hf.co/codefuse-ai/SWE-CARE-RM
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- config.json +30 -0
- data_sample.jsonl +1 -0
- eval_result.json +8 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +406 -0
- projector.pth +3 -0
- reward_config.json +11 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 12288,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 36,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.51.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
data_sample.jsonl
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"problem_statement": "Louisiana itemized deductions\nref:\r\nhttps://revenue.louisiana.gov/TaxForms/IT540WEB(2022)%20F%20D2.pdf (page2) \r\nhttps://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf (page 2, line 8A-8D) \r\nhttps://www.irs.gov/pub/irs-pdf/f1040sa.pdf (federal itemized deductions) \r\nhttps://legis.la.gov/legis/Law.aspx?d=101760", "patch_to_review": "diff --git a/changelog_entry.yaml b/changelog_entry.yaml\nindex e69de29bb2d..ec51656d252 100644\n--- a/changelog_entry.yaml\n+++ b/changelog_entry.yaml\n@@ -0,0 +1,4 @@\n+- bump: minor\n+ changes:\n+ added:\n+ - Louisiana itemized deductions.\ndiff --git a/policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/limit_to_medical_expense_deduction.yaml b/policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/limit_to_medical_expense_deduction.yaml\nnew file mode 100644\nindex 00000000000..a230ae7368f\n--- /dev/null\n+++ b/policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/limit_to_medical_expense_deduction.yaml\n@@ -0,0 +1,16 @@\n+description: Louisiana subtracts from adjusted gross income the excess of the federal medical expense deduction over the standard deduction if this is true.\n+values:\n+ 2021-01-01: False \n+ 2022-01-01: True\n+\n+metadata:\n+ unit: bool\n+ period: year\n+ label: Louisiana itemized deduction medical expense exceedance availability\n+ reference:\n+ - title: Louisiana legal code | RS 47:293 (3)\n+ href: https://www.legis.la.gov/Legis/Law.aspx?d=101760\n+ - title: General Information for Filing Your 2022 Louisiana Resident Individual Income Tax Return, page 2\n+ href: https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\n+ - title: General Information for Filing Your 2021 Louisiana Resident Individual Income Tax Return, page 1\n+ href: https://revenue.louisiana.gov/TaxForms/IT540i(2021)%20Instructions.pdf#page=3\ndiff --git a/policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml b/policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml\nnew file mode 100644\nindex 00000000000..e59ef6cd067\n--- /dev/null\n+++ b/policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml\n@@ -0,0 +1,15 @@\n+description: Louisiana subtracts from adjusted gross income this fraction of the excess of the federal medical itemized deduction over the federal standard deduction.\n+values:\n+ 2022-01-01: 1\n+\n+metadata:\n+ unit: /1\n+ period: year\n+ label: Louisiana excess itemized deduction fraction\n+ reference:\n+ # This policy parameter was introduced in 2022\n+ - title: Louisiana legal code | RS 47:293 (3)\n+ href: https://www.legis.la.gov/Legis/Law.aspx?d=101760\n+ - title: General Information for Filing Your 2022 Louisiana Resident Individual Income Tax Return, page 2\n+ href: https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\n+\ndiff --git a/policyengine_us/tests/policy/baseline/gov/states/la/tax/income/deductions/la_itemized_deductions.yaml b/policyengine_us/tests/policy/baseline/gov/states/la/tax/income/deductions/la_itemized_deductions.yaml\nnew file mode 100644\nindex 00000000000..8fbc3210544\n--- /dev/null\n+++ b/policyengine_us/tests/policy/baseline/gov/states/la/tax/income/deductions/la_itemized_deductions.yaml\n@@ -0,0 +1,72 @@\n+- name: Outside Louisiana, no Louisiana deductions\n+ period: 2022\n+ input:\n+ state_code: NY\n+ standard_deduction: 12_950\n+ tax_unit_itemizes: false\n+ output:\n+ la_itemized_deductions: 0\n+\n+- name: 2022 Louisiana deduction given Single status, with medical expense deduction 20_000\n+ period: 2022\n+ input:\n+ state_code: LA\n+ standard_deduction: 12_950\n+ medical_expense_deduction: 20_000\n+ tax_unit_itemizes: true\n+ output:\n+ la_itemized_deductions: 7_050\n+\n+- name: 2022 Louisiana deduction given Single status, with medical expense deduction 20_000\n+ period: 2022\n+ input:\n+ state_code: LA\n+ standard_deduction: 12_950\n+ medical_expense_deduction: 20_000\n+ tax_unit_itemizes: true\n+ output:\n+ la_itemized_deductions: 7_050\n+\n+- name: 2021 Louisiana deduction given Single status, with federal itemized deductions 30_000\n+ period: 2021\n+ input:\n+ state_code: LA\n+ standard_deduction: 12_550\n+ medical_expense_deduction: 20_000\n+ itemized_deductions_less_salt: 30_000\n+ tax_unit_itemizes: true\n+ output:\n+ la_itemized_deductions: 17_450\n+ #30_000-12_550\n+\n+- name: 2021 Louisiana deduction given Single status, with federal itemized deductions 10_000\n+ period: 2021\n+ input:\n+ state_code: LA\n+ standard_deduction: 12_550\n+ medical_expense_deduction: 20_000\n+ itemized_deductions_less_salt: 10_000\n+ tax_unit_itemizes: true\n+ output:\n+ la_itemized_deductions: 0\n+ #10_000-12_550<0\n+\n+- name: 2022 Louisiana deduction given Head of Household status, with medical expense deduction 20_000\n+ period: 2022\n+ input:\n+ state_code: LA\n+ standard_deduction: 19_400\n+ medical_expense_deduction: 20_000\n+ tax_unit_itemizes: true\n+ output:\n+ la_itemized_deductions: 600\n+\n+- name: 2022 Louisiana deduction given Head of Widow status, with medical expense deduction 20_000\n+ period: 2022\n+ input:\n+ state_code: LA\n+ standard_deduction: 25_900\n+ medical_expense_deduction: 20_000\n+ tax_unit_itemizes: true\n+ output:\n+ la_itemized_deductions: 0\ndiff --git a/policyengine_us/tests/policy/baseline/gov/states/la/tax/income/la_taxable_income.yaml b/policyengine_us/tests/policy/baseline/gov/states/la/tax/income/la_taxable_income.yaml\nnew file mode 100644\nindex 00000000000..7dfc98724f8\n--- /dev/null\n+++ b/policyengine_us/tests/policy/baseline/gov/states/la/tax/income/la_taxable_income.yaml\n@@ -0,0 +1,19 @@\n+- name: Unit test 1\n+ period: 2020\n+ input:\n+ state_code: LA\n+ adjusted_gross_income: 3_000\n+ la_itemized_deductions: 1_000\n+ la_exemptions: 1_000\n+ output:\n+ la_taxable_income: 1_000 #3_000-1_000-1_000=1_000>0 \n+\n+- name: Unit test 2\n+ period: 2020\n+ input:\n+ state_code: LA\n+ adjusted_gross_income: 3_000\n+ la_itemized_deductions: 2_000\n+ la_exemptions: 2_000\n+ output:\n+ la_taxable_income: 0 #3_000-2_000-2_000<0 \ndiff --git a/policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py b/policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py\nnew file mode 100644\nindex 00000000000..ae58a3c8537\n--- /dev/null\n+++ b/policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py\n@@ -0,0 +1,49 @@\n+from policyengine_us.model_api import *\n+\n+\n+class la_itemized_deductions(Variable):\n+ value_type = float\n+ entity = TaxUnit\n+ label = \"Louisiana itemized deduction\"\n+ unit = USD\n+ definition_period = YEAR\n+ reference = [\n+ \"https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\", # 2022 line 8B-line 8C\n+ \"https://revenue.louisiana.gov/TaxForms/IT540i(2021)%20Instructions.pdf#page=3\", # 2021 line 8A-line 8C\n+ \"https://www.legis.la.gov/Legis/Law.aspx?d=101760\", # (3)\n+ ]\n+ defined_for = StateCode.LA\n+\n+ def formula(tax_unit, period, parameters):\n+ p = parameters(\n+ period\n+ ).gov.states.la.tax.income.deductions.itemized.medical_expenses.exceedance\n+ us_standard_deduction = tax_unit(\"standard_deduction\", period)\n+ itemizing = tax_unit(\"tax_unit_itemizes\", period)\n+ # In 2022 Louisiana limits the itemized deductions to the amount of federal medical\n+ # expense deduction less the federal standard deduction\n+ if p.limit_to_medical_expense_deduction:\n+ # In the legal code the deduction is multiplied by a certain rate, which is not\n+ # represented in the tax form\n+ medical_expense_deduction = add(\n+ tax_unit, period, [\"medical_expense_deduction\"]\n+ )\n+ medical_exepense_ded_less_standard_ded = (\n+ max_(medical_expense_deduction - us_standard_deduction, 0)\n+ * p.rate\n+ )\n+ return where(\n+ itemizing, medical_exepense_ded_less_standard_ded, 0\n+ ) # 2022 itemized deductions\n+ # In 2021 Louisiana limits the state itemized deductions value to the value of the federal\n+ # itemized deductions less the federal standard deduction\n+ else:\n+ us_itemized_deduction = tax_unit(\n+ \"itemized_deductions_less_salt\", period\n+ )\n+ itemized_less_standard_ded = max_(\n+ 0, us_itemized_deduction - us_standard_deduction\n+ )\n+ return where(\n+ itemizing, itemized_less_standard_ded, 0\n+ ) # 2021 itemized deductions\ndiff --git a/policyengine_us/variables/gov/states/la/tax/income/la_exemptions.py b/policyengine_us/variables/gov/states/la/tax/income/la_exemptions.py\nnew file mode 100644\nindex 00000000000..22992b14472\n--- /dev/null\n+++ b/policyengine_us/variables/gov/states/la/tax/income/la_exemptions.py\n@@ -0,0 +1,10 @@\n+from policyengine_us.model_api import *\n+\n+\n+class la_exemptions(Variable):\n+ value_type = float\n+ entity = TaxUnit\n+ label = \"Louisiana exemptions\"\n+ unit = USD\n+ definition_period = YEAR\n+ defined_for = StateCode.LA\ndiff --git a/policyengine_us/variables/gov/states/la/tax/income/la_taxable_income.py b/policyengine_us/variables/gov/states/la/tax/income/la_taxable_income.py\nindex 615665798cd..2564ba7a6fc 100644\n--- a/policyengine_us/variables/gov/states/la/tax/income/la_taxable_income.py\n+++ b/policyengine_us/variables/gov/states/la/tax/income/la_taxable_income.py\n@@ -8,3 +8,11 @@ class la_taxable_income(Variable):\n defined_for = StateCode.LA\n unit = USD\n definition_period = YEAR\n+\n+ def formula(tax_unit, period, parameters):\n+ return max_(\n+ tax_unit(\"adjusted_gross_income\", period)\n+ - tax_unit(\"la_itemized_deductions\", period)\n+ - tax_unit(\"la_exemptions\", period),\n+ 0,\n+ )\ndiff --git a/policyengine_us/variables/gov/states/tax/income/state_income_tax.py b/policyengine_us/variables/gov/states/tax/income/state_income_tax.py\nindex 6e40e5ccac3..afb5a2f5261 100644\n--- a/policyengine_us/variables/gov/states/tax/income/state_income_tax.py\n+++ b/policyengine_us/variables/gov/states/tax/income/state_income_tax.py\n@@ -27,7 +27,7 @@ class state_income_tax(Variable):\n \"in_income_tax\",\n \"ks_income_tax\",\n \"ky_income_tax\",\n- \"la_income_tax\",\n+ # \"la_income_tax\", --- activating will cause circular logic errors\n # \"ma_income_tax\", --- activating will cause circular logic errors\n # \"md_income_tax\", --- activating will cause circular logic errors\n # \"me_income_tax\", --- activating will cause circular logic errors\n", "pos_review": ["<code>\n[start of policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py]\n 1 from policyengine_us.model_api import *\n 2 \n 3 \n 4 class la_itemized_deductions(Variable):\n 5 value_type = float\n 6 entity = TaxUnit\n 7 label = \"Louisiana itemized deduction\"\n 8 unit = USD\n 9 definition_period = YEAR\n 10 reference = [\n 11 \"https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\", # 2022 line 8B-line 8C\n 12 \"https://revenue.louisiana.gov/TaxForms/IT540i(2021)%20Instructions.pdf#page=3\", # 2021 line 8A-line 8C\n 13 \"https://www.legis.la.gov/Legis/Law.aspx?d=101760\", # (3)\n 14 ]\n 15 defined_for = StateCode.LA\n 16 \n 17 def formula(tax_unit, period, parameters):\n 18 p = parameters(\n 19 period\n 20 ).gov.states.la.tax.income.deductions.itemized.medical_expenses.exceedance\n 21 us_standard_deduction = tax_unit(\"standard_deduction\", period)\n 22 itemizing = tax_unit(\"tax_unit_itemizes\", period)\n 23 # In 2022 Louisiana limits the itemized deductions to the amount of federal medical\n 24 # expense deduction less the federal standard deduction\n 25 if p.limit_to_medical_expense_deduction:\n 26 # In the legal code the deduction is multiplied by a certain rate, which is not\n 27 # represented in the tax form\n 28 medical_expense_deduction = add(\n 29 tax_unit, period, [\"medical_expense_deduction\"]\n 30 )\n 31 medical_exepense_ded_less_standard_ded = (\n 32 max_(medical_expense_deduction - us_standard_deduction, 0)\n 33 * p.rate\n 34 )\n 35 return where(\n 36 itemizing, medical_exepense_ded_less_standard_ded, 0\n 37 ) # 2022 itemized deductions\n 38 # In 2021 Louisiana limits the state itemized deductions value to the value of the federal\n 39 # itemized deductions less the federal standard deduction\n 40 else:\n 41 us_itemized_deduction = tax_unit(\n 42 \"itemized_deductions_less_salt\", period\n 43 )\n 44 itemized_less_standard_ded = max_(\n 45 0, us_itemized_deduction - us_standard_deduction\n 46 )\n 47 return where(\n 48 itemizing, itemized_less_standard_ded, 0\n 49 ) # 2021 itemized deductions\n 50 \n[end of policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py]\n</code>\n<diff_hunk>\n@@ -0,0 +1,49 @@\n+from policyengine_us.model_api import *\n+\n+\n+class la_itemized_deductions(Variable):\n+ value_type = float\n+ entity = TaxUnit\n+ label = \"Louisiana itemized deduction\"\n+ unit = USD\n+ definition_period = YEAR\n+ reference = [\n+ \"https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\", # 2022 line 8B-line 8C\n+ \"https://revenue.louisiana.gov/TaxForms/IT540i(2021)%20Instructions.pdf#page=3\", # 2021 line 8A-line 8C\n+ \"https://www.legis.la.gov/Legis/Law.aspx?d=101760\", # (3)\n+ ]\n+ defined_for = StateCode.LA\n+\n+ def formula(tax_unit, period, parameters):\n+ p = parameters(\n+ period\n+ ).gov.states.la.tax.income.deductions.itemized.medical_expenses.exceedance\n+ us_standard_deduction = tax_unit(\"standard_deduction\", period)\n+ itemizing = tax_unit(\"tax_unit_itemizes\", period)\n+ # In 2022 Louisiana limits the itemized deductions to the amount of federal medical\n+ # expense deduction less the federal standard deduction\n+ if p.limit_to_medical_expense_deduction:\n+ # In the legal code the deduction is multiplied by a certain rate, which is not\n+ # represented in the tax form\n+ medical_expense_deduction = add(\n+ tax_unit, period, [\"medical_expense_deduction\"]\n+ )\n+ medical_exepense_ded_less_standard_ded = (\n+ max_(medical_expense_deduction - us_standard_deduction, 0)\n+ * p.rate\n+ )\n+ return where(\n+ itemizing, medical_exepense_ded_less_standard_ded, 0\n+ ) # 2022 itemized deductions\n+ # In 2021 Louisiana limits the state itemized deductions value to the value of the federal\n+ # itemized deductions less the federal standard deduction\n+ else:\n+ us_itemized_deduction = tax_unit(\n</diff_hunk>\n<path>policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py</path>\n<line>41</line>\n<review_comment>\n@user1:\n```suggestion\r\n federal_itemized_deduction = tax_unit(\r\n```\n</review_comment>", "<code>\n[start of policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py]\n 1 from policyengine_us.model_api import *\n 2 \n 3 \n 4 class la_itemized_deductions(Variable):\n 5 value_type = float\n 6 entity = TaxUnit\n 7 label = \"Louisiana itemized deduction\"\n 8 unit = USD\n 9 definition_period = YEAR\n 10 reference = [\n 11 \"https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\", # 2022 line 8B-line 8C\n 12 \"https://revenue.louisiana.gov/TaxForms/IT540i(2021)%20Instructions.pdf#page=3\", # 2021 line 8A-line 8C\n 13 \"https://www.legis.la.gov/Legis/Law.aspx?d=101760\", # (3)\n 14 ]\n 15 defined_for = StateCode.LA\n 16 \n 17 def formula(tax_unit, period, parameters):\n 18 p = parameters(\n 19 period\n 20 ).gov.states.la.tax.income.deductions.itemized.medical_expenses.exceedance\n 21 us_standard_deduction = tax_unit(\"standard_deduction\", period)\n 22 itemizing = tax_unit(\"tax_unit_itemizes\", period)\n 23 # In 2022 Louisiana limits the itemized deductions to the amount of federal medical\n 24 # expense deduction less the federal standard deduction\n 25 if p.limit_to_medical_expense_deduction:\n 26 # In the legal code the deduction is multiplied by a certain rate, which is not\n 27 # represented in the tax form\n 28 medical_expense_deduction = add(\n 29 tax_unit, period, [\"medical_expense_deduction\"]\n 30 )\n 31 medical_exepense_ded_less_standard_ded = (\n 32 max_(medical_expense_deduction - us_standard_deduction, 0)\n 33 * p.rate\n 34 )\n 35 return where(\n 36 itemizing, medical_exepense_ded_less_standard_ded, 0\n 37 ) # 2022 itemized deductions\n 38 # In 2021 Louisiana limits the state itemized deductions value to the value of the federal\n 39 # itemized deductions less the federal standard deduction\n 40 else:\n 41 us_itemized_deduction = tax_unit(\n 42 \"itemized_deductions_less_salt\", period\n 43 )\n 44 itemized_less_standard_ded = max_(\n 45 0, us_itemized_deduction - us_standard_deduction\n 46 )\n 47 return where(\n 48 itemizing, itemized_less_standard_ded, 0\n 49 ) # 2021 itemized deductions\n 50 \n[end of policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py]\n</code>\n<diff_hunk>\n@@ -0,0 +1,49 @@\n+from policyengine_us.model_api import *\n+\n+\n+class la_itemized_deductions(Variable):\n+ value_type = float\n+ entity = TaxUnit\n+ label = \"Louisiana itemized deduction\"\n+ unit = USD\n+ definition_period = YEAR\n+ reference = [\n+ \"https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\", # 2022 line 8B-line 8C\n+ \"https://revenue.louisiana.gov/TaxForms/IT540i(2021)%20Instructions.pdf#page=3\", # 2021 line 8A-line 8C\n+ \"https://www.legis.la.gov/Legis/Law.aspx?d=101760\", # (3)\n+ ]\n+ defined_for = StateCode.LA\n+\n+ def formula(tax_unit, period, parameters):\n+ p = parameters(\n+ period\n+ ).gov.states.la.tax.income.deductions.itemized.medical_expenses.exceedance\n+ us_standard_deduction = tax_unit(\"standard_deduction\", period)\n</diff_hunk>\n<path>policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py</path>\n<line>21</line>\n<review_comment>\n@user1:\n```suggestion\r\n federal_standard_deduction = tax_unit(\"standard_deduction\", period)\r\n```\n</review_comment>", "<code>\n[start of policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py]\n 1 from policyengine_us.model_api import *\n 2 \n 3 \n 4 class la_itemized_deductions(Variable):\n 5 value_type = float\n 6 entity = TaxUnit\n 7 label = \"Louisiana itemized deduction\"\n 8 unit = USD\n 9 definition_period = YEAR\n 10 reference = [\n 11 \"https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\", # 2022 line 8B-line 8C\n 12 \"https://revenue.louisiana.gov/TaxForms/IT540i(2021)%20Instructions.pdf#page=3\", # 2021 line 8A-line 8C\n 13 \"https://www.legis.la.gov/Legis/Law.aspx?d=101760\", # (3)\n 14 ]\n 15 defined_for = StateCode.LA\n 16 \n 17 def formula(tax_unit, period, parameters):\n 18 p = parameters(\n 19 period\n 20 ).gov.states.la.tax.income.deductions.itemized.medical_expenses.exceedance\n 21 us_standard_deduction = tax_unit(\"standard_deduction\", period)\n 22 itemizing = tax_unit(\"tax_unit_itemizes\", period)\n 23 # In 2022 Louisiana limits the itemized deductions to the amount of federal medical\n 24 # expense deduction less the federal standard deduction\n 25 if p.limit_to_medical_expense_deduction:\n 26 # In the legal code the deduction is multiplied by a certain rate, which is not\n 27 # represented in the tax form\n 28 medical_expense_deduction = add(\n 29 tax_unit, period, [\"medical_expense_deduction\"]\n 30 )\n 31 medical_exepense_ded_less_standard_ded = (\n 32 max_(medical_expense_deduction - us_standard_deduction, 0)\n 33 * p.rate\n 34 )\n 35 return where(\n 36 itemizing, medical_exepense_ded_less_standard_ded, 0\n 37 ) # 2022 itemized deductions\n 38 # In 2021 Louisiana limits the state itemized deductions value to the value of the federal\n 39 # itemized deductions less the federal standard deduction\n 40 else:\n 41 us_itemized_deduction = tax_unit(\n 42 \"itemized_deductions_less_salt\", period\n 43 )\n 44 itemized_less_standard_ded = max_(\n 45 0, us_itemized_deduction - us_standard_deduction\n 46 )\n 47 return where(\n 48 itemizing, itemized_less_standard_ded, 0\n 49 ) # 2021 itemized deductions\n 50 \n[end of policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py]\n</code>\n<diff_hunk>\n@@ -0,0 +1,49 @@\n+from policyengine_us.model_api import *\n+\n+\n+class la_itemized_deductions(Variable):\n+ value_type = float\n+ entity = TaxUnit\n+ label = \"Louisiana itemized deduction\"\n</diff_hunk>\n<path>policyengine_us/variables/gov/states/la/tax/income/deductions/la_itemized_deductions.py</path>\n<line>7</line>\n<review_comment>\n@user1:\n```suggestion\r\n label = \"Louisiana itemized deductions\"\r\n```\n</review_comment>", "<code>\n[start of policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml]\n 1 description: Louisiana subtracts from adjusted gross income this fraction of the excess of the federal medical itemized deduction over the federal standard deduction.\n 2 values:\n 3 2022-01-01: 1\n 4 \n 5 metadata:\n 6 unit: /1\n 7 period: year\n 8 label: Louisiana excess itemized deduction fraction\n 9 reference:\n 10 # This policy parameter was introduced in 2022\n 11 - title: Louisiana legal code | RS 47:293 (3)\n 12 href: https://www.legis.la.gov/Legis/Law.aspx?d=101760\n 13 - title: General Information for Filing Your 2022 Louisiana Resident Individual Income Tax Return, page 2\n 14 href: https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\n 15 \n 16 \n[end of policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml]\n</code>\n<diff_hunk>\n@@ -0,0 +1,15 @@\n+description: Louisiana subtracts from adjusted gross income this fraction of the excess of the federal medical itemized deduction over the federal standard deduction.\n</diff_hunk>\n<path>policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml</path>\n<line>1</line>\n<review_comment>\n@user1:\n```suggestion\r\ndescription: Louisiana subtracts this fraction of the excess of the either the federal itemized deductions or the medical expense deduction amount over the federal standard deduction from adjusted gross income.\r\n```\n</review_comment>", "<code>\n[start of policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml]\n 1 description: Louisiana subtracts from adjusted gross income this fraction of the excess of the federal medical itemized deduction over the federal standard deduction.\n 2 values:\n 3 2022-01-01: 1\n 4 \n 5 metadata:\n 6 unit: /1\n 7 period: year\n 8 label: Louisiana excess itemized deduction fraction\n 9 reference:\n 10 # This policy parameter was introduced in 2022\n 11 - title: Louisiana legal code | RS 47:293 (3)\n 12 href: https://www.legis.la.gov/Legis/Law.aspx?d=101760\n 13 - title: General Information for Filing Your 2022 Louisiana Resident Individual Income Tax Return, page 2\n 14 href: https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\n 15 \n 16 \n[end of policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml]\n</code>\n<diff_hunk>\n@@ -0,0 +1,15 @@\n+description: Louisiana subtracts from adjusted gross income this fraction of the excess of the federal medical itemized deduction over the federal standard deduction.\n+values:\n+ 2022-01-01: 1\n+\n+metadata:\n+ unit: /1\n+ period: year\n+ label: Louisiana excess itemized deduction fraction\n</diff_hunk>\n<path>policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml</path>\n<line>8</line>\n<review_comment>\n@user1:\n```suggestion\r\n label: Louisiana itemized deduction excess fraction\r\n```\n</review_comment>"], "neg_review": ["<code>\n[start of policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml]\n 1 description: Louisiana subtracts from adjusted gross income this fraction of the excess of the federal medical itemized deduction over the federal standard deduction.\n 2 values:\n 3 2022-01-01: 1\n 4 \n 5 metadata:\n 6 unit: /1\n 7 period: year\n 8 label: Louisiana excess itemized deduction fraction\n 9 reference:\n 10 # This policy parameter was introduced in 2022\n 11 - title: Louisiana legal code | RS 47:293 (3)\n 12 href: https://www.legis.la.gov/Legis/Law.aspx?d=101760\n 13 - title: General Information for Filing Your 2022 Louisiana Resident Individual Income Tax Return, page 2\n 14 href: https://revenue.louisiana.gov/TaxForms/IT540iWEB(2022)D1.pdf#page=2\n 15 \n 16 \n[end of policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml]\n</code>\n<diff_hunk>\n\n</diff_hunk>\n<path>policyengine_us/parameters/gov/states/la/tax/income/deductions/itemized/medical_expenses/exceedance/rate.yaml</path>\n<line></line>\n<review_comment>\n@user1:\nrename to excess_fraction.yaml\n</review_comment>"], "metadata": {"repo": "PolicyEngine/policyengine-us", "pr_number": 2541, "url": "https://github.com/PolicyEngine/policyengine-us/pull/2541", "commit_to_review": "16cbda8bc64c6489bc5e266db8373b03b340d82c", "file_source": "reviewed_file"}}
|
eval_result.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_accuracy": 0.75,
|
| 3 |
+
"point_accuracy": 0.9,
|
| 4 |
+
"point_precision": 0.9411764705882353,
|
| 5 |
+
"point_recall": 0.9411764705882353,
|
| 6 |
+
"point_f1": 0.9411764705882353,
|
| 7 |
+
"point_auc": 0.8431372549019609
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.1"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4387547b5858eeef209a768b4a27488e7a9f46fc78152dffb5f51f314b2e66c9
|
| 3 |
+
size 6462635368
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16381470720
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 405 |
+
}
|
| 406 |
+
}
|
projector.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d711a754c3c11d499315d9d0685fc8cf267555dd5ef976f224d2e1d144ec97d
|
| 3 |
+
size 33572832
|
reward_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"format_version": 1,
|
| 3 |
+
"base_model_dir": "/ainative/muti-modal/yuhang/415350/download_models/Qwen3-8B",
|
| 4 |
+
"lora_dir": "/ainative/muti-modal/yuhang/415350/trained_reward_models/v2.2/step_2200/decoder",
|
| 5 |
+
"projector_path": "projector.pth",
|
| 6 |
+
"proj_arch": "mlp2x_relu",
|
| 7 |
+
"torch_dtype": "bfloat16",
|
| 8 |
+
"attn_implementation": null,
|
| 9 |
+
"trust_remote_code": true,
|
| 10 |
+
"reward_activation": "sigmoid"
|
| 11 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"padding_side": "left",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|